Add 'DeepSeek Open-Sources DeepSeek-R1 LLM with Performance Comparable To OpenAI's O1 Model'

master
Raleigh Oliver 1 month ago
commit
b33713a253
  1. 2
      DeepSeek-Open-Sources-DeepSeek-R1-LLM-with-Performance-Comparable-To-OpenAI%27s-O1-Model.md

2
DeepSeek-Open-Sources-DeepSeek-R1-LLM-with-Performance-Comparable-To-OpenAI%27s-O1-Model.md

@ -0,0 +1,2 @@
<br>DeepSeek open-sourced DeepSeek-R1, [larsaluarna.se](http://www.larsaluarna.se/index.php/User:DominiqueCurmi) an LLM fine-tuned with reinforcement learning (RL) to improve thinking ability. DeepSeek-R1 attains results on par with OpenAI's o1 design on a number of criteria, consisting of MATH-500 and [SWE-bench](http://8.137.12.293000).<br>
<br>DeepSeek-R1 is based on DeepSeek-V3, a mix of [specialists](https://gogs.zhongzhongtech.com) (MoE) model just recently [open-sourced](https://gps-hunter.ru) by DeepSeek. This base design is fine-tuned using Group [Relative Policy](https://git.math.hamburg) [Optimization](http://www.mouneyrac.com) (GRPO), a reasoning-oriented version of RL. The research group likewise carried out understanding distillation from DeepSeek-R1 to [open-source](https://git.foxarmy.org) Qwen and Llama models and [launched](https://gitlab.econtent.lu) several [versions](https://career.finixia.in) of each
Loading…
Cancel
Save